Chemometrics and Intelligent Laboratory Systems最新文献_第4页

Surface-enhanced Raman spectroscopy combined with chemometrics for quantitative analysis and carcinogenic risk estimation of polycyclic aromatic hydrocarbons in water with complex matrix

IF 3.7 2区化学 Q2 AUTOMATION & CONTROL SYSTEMS

Chemometrics and Intelligent Laboratory Systems

Pub Date : 2024-12-01 DOI: 10.1016/j.chemolab.2024.105293

Rongling Zhang , Mengjun Guo , Maogang Li , Hongsheng Tang , Tianlong Zhang , Hua Li

Polycyclic aromatic hydrocarbons (PAHs) as a kind of persistent organic pollutants have high teratogenic, carcinogenic, mutagenic properties, as well as high octanol/water partition coefficient and sediment/water partition coefficient, causing serious threat to human health and water environment. In this study, the feasibility of Surface-enhanced Raman spectroscopy (SERS) technology combined with chemometrics for quantitative analysis and carcinogenic risk estimation of PAHs in water with complex matrix was explored. Firstly, 36 water samples from lake, tap, and distilled water were prepared, and then nano-silver particles (Ag NPs) were mixed with samples. The integrated strategy of spectral preprocessing was adopted to remove spectral interference, and variable selection algorithm was used to extract the information effectively, thus improving the prediction performance of the random forest (RF) calibration model for PAHs quantitative analysis and carcinogenic risk. The final results indicated that RF combined with spectral preprocessing integration strategy and variable selection had better predictive performance compared with the Raw-RF model. For phenanthrene (Phe) and benzo[a]anthracene (BaA) analysis, the optimal calibration model was WT-SG-SiPLS-VIM-RF (Phe: mean relative error of prediction (MRE_p) = 0.0646, coefficient of determination of prediction (R²_p) = 0.9658; BaA: MRE_p = 0.0949, R²_p = 0.9537). SG-WT-SiPLS-VIM-RF model (MRE_p = 0.0992, R²_p = 0.9551) showed a better predictive performance for fluoranthene (Flu). WT-SG-VIM-RF model (MRE_p = 0.0902, R²_p = 0.9409) showed excellent performance for assessing the carcinogenic risk of PAHs. Therefore, the combination of SERS technology and chemometrics provides a new approach for analyzing PAHs.

{"title":"Surface-enhanced Raman spectroscopy combined with chemometrics for quantitative analysis and carcinogenic risk estimation of polycyclic aromatic hydrocarbons in water with complex matrix","authors":"Rongling Zhang , Mengjun Guo , Maogang Li , Hongsheng Tang , Tianlong Zhang , Hua Li","doi":"10.1016/j.chemolab.2024.105293","DOIUrl":"10.1016/j.chemolab.2024.105293","url":null,"abstract":"<div><div>Polycyclic aromatic hydrocarbons (PAHs) as a kind of persistent organic pollutants have high teratogenic, carcinogenic, mutagenic properties, as well as high octanol/water partition coefficient and sediment/water partition coefficient, causing serious threat to human health and water environment. In this study, the feasibility of Surface-enhanced Raman spectroscopy (SERS) technology combined with chemometrics for quantitative analysis and carcinogenic risk estimation of PAHs in water with complex matrix was explored. Firstly, 36 water samples from lake, tap, and distilled water were prepared, and then nano-silver particles (Ag NPs) were mixed with samples. The integrated strategy of spectral preprocessing was adopted to remove spectral interference, and variable selection algorithm was used to extract the information effectively, thus improving the prediction performance of the random forest (RF) calibration model for PAHs quantitative analysis and carcinogenic risk. The final results indicated that RF combined with spectral preprocessing integration strategy and variable selection had better predictive performance compared with the Raw-RF model. For phenanthrene (Phe) and benzo[<em>a</em>]anthracene (BaA) analysis, the optimal calibration model was WT-SG-SiPLS-VIM-RF (Phe: mean relative error of prediction (MRE<sub>p</sub>) = 0.0646, coefficient of determination of prediction (R<sup>2</sup><sub>p</sub>) = 0.9658; BaA: MRE<sub>p</sub> = 0.0949, R<sup>2</sup><sub>p</sub> = 0.9537). SG-WT-SiPLS-VIM-RF model (MRE<sub>p</sub> = 0.0992, R<sup>2</sup><sub>p</sub> = 0.9551) showed a better predictive performance for fluoranthene (Flu). WT-SG-VIM-RF model (MRE<sub>p</sub> = 0.0902, R<sup>2</sup><sub>p</sub> = 0.9409) showed excellent performance for assessing the carcinogenic risk of PAHs. Therefore, the combination of SERS technology and chemometrics provides a new approach for analyzing PAHs.</div></div>","PeriodicalId":9774,"journal":{"name":"Chemometrics and Intelligent Laboratory Systems","volume":"257 ","pages":"Article 105293"},"PeriodicalIF":3.7,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143156198","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Exploring NIR spectroscopy data: A practical chemometric tutorial for analyzing freeze-dried pharmaceutical formulations

IF 3.7 2区化学 Q2 AUTOMATION & CONTROL SYSTEMS

Chemometrics and Intelligent Laboratory Systems

Pub Date : 2024-11-30 DOI: 10.1016/j.chemolab.2024.105291

Ambra Massei , Nicola Cavallini , Francesco Savorani , Nunzia Falco , Davide Fissore

Chemometrics tools are of fundamental importance for data analysis in the pharmaceutical field, especially with the increasingly strong assertion of the Process Analytical Technologies (PAT). In fact, analytical technologies such as Near-Infrared or Raman spectroscopies generate a lot of data, the spectra, that must be analyzed in a proper way. Typically, it is quite difficult to deeply understand the information hidden within the raw data. Therefore, careful, and efficient data exploration is needed to highlight the chemical and physical features of the analyzed samples.

Here, a tutorial on all the fundamental steps and concepts needed to perform a proper data analysis based on a case-study of different freeze-dried formulations in the pharmaceutical field is proposed. The data analysis pipeline begins with the dataset explanation, to better point out the main known differences and similarities among the investigated formulations. After the first step of data preprocessing, Principal Component Analysis (PCA), Partial Least Squares (PLS) for regression, and Partial Least Squares-Discriminant Analysis (PLS-DA) for classification are presented and applied to show how to obtain deep comprehension of the real-case NIR dataset at hand. The experimental results demonstrate that trends related to increasing levels of sucrose and/or arginine, as well as distinct clusters related to the sample type and to the operator who conducted the analysis can be found and modelled in the example data.

The tutorial aims at providing clear practical steps to conduct a robust data analysis, starting from the extraction and organization of the raw data, up to building more advanced predictive models (regression and classification). At each step some key questions are asked and answered to stimulate critical thinking in the reader. Also, commented MATLAB scripts are provided together with the real-case example NIR data, so that anyone could reproduce the whole data analysis in the tutorial, and try first hand to work with the data.

{"title":"Exploring NIR spectroscopy data: A practical chemometric tutorial for analyzing freeze-dried pharmaceutical formulations","authors":"Ambra Massei , Nicola Cavallini , Francesco Savorani , Nunzia Falco , Davide Fissore","doi":"10.1016/j.chemolab.2024.105291","DOIUrl":"10.1016/j.chemolab.2024.105291","url":null,"abstract":"<div><div>Chemometrics tools are of fundamental importance for data analysis in the pharmaceutical field, especially with the increasingly strong assertion of the Process Analytical Technologies (PAT). In fact, analytical technologies such as Near-Infrared or Raman spectroscopies generate a lot of data, the spectra, that must be analyzed in a proper way. Typically, it is quite difficult to deeply understand the information hidden within the raw data. Therefore, careful, and efficient data exploration is needed to highlight the chemical and physical features of the analyzed samples.</div><div>Here, a tutorial on all the fundamental steps and concepts needed to perform a proper data analysis based on a case-study of different freeze-dried formulations in the pharmaceutical field is proposed. The data analysis pipeline begins with the dataset explanation, to better point out the main known differences and similarities among the investigated formulations. After the first step of data preprocessing, Principal Component Analysis (PCA), Partial Least Squares (PLS) for regression, and Partial Least Squares-Discriminant Analysis (PLS-DA) for classification are presented and applied to show how to obtain deep comprehension of the real-case NIR dataset at hand. The experimental results demonstrate that trends related to increasing levels of sucrose and/or arginine, as well as distinct clusters related to the sample type and to the operator who conducted the analysis can be found and modelled in the example data.</div><div>The tutorial aims at providing clear practical steps to conduct a robust data analysis, starting from the extraction and organization of the raw data, up to building more advanced predictive models (regression and classification). At each step some key questions are asked and answered to stimulate critical thinking in the reader. Also, commented MATLAB scripts are provided together with the real-case example NIR data, so that anyone could reproduce the whole data analysis in the tutorial, and try first hand to work with the data.</div></div>","PeriodicalId":9774,"journal":{"name":"Chemometrics and Intelligent Laboratory Systems","volume":"257 ","pages":"Article 105291"},"PeriodicalIF":3.7,"publicationDate":"2024-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143155126","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Sparse attention regression network-based soil fertility prediction with UMMASO

IF 3.7 2区化学 Q2 AUTOMATION & CONTROL SYSTEMS

Chemometrics and Intelligent Laboratory Systems

Pub Date : 2024-11-28 DOI: 10.1016/j.chemolab.2024.105289

RVRaghavendra Rao , U Srinivasulu Reddy

The challenge of imbalanced soil nutrient datasets significantly hampers accurate predictions of soil fertility. To tackle this, a new method is suggested in this research, combining Uniform Manifold Approximation and Projection (UMAP) with Least Absolute Shrinkage and Selection Operator (LASSO). The main aim is to counter the impact of uneven data distribution and improve soil fertility models' predictive precision. The model introduced uses Sparse Attention Regression, effectively incorporating pertinent features from the imbalanced dataset. UMAP is utilised initially to reduce data complexity, unveiling hidden structures and essential patterns. Following this, LASSO is applied to refine features and enhance the model's interpretability. The experimental outcomes highlight the effectiveness of the UMAP and LASSO hybrid approach. The proposed model achieves outstanding performance metrics, reaching a predictive accuracy of 98 %, demonstrating its capability in accurate soil fertility predictions. It also showcases a Precision of 91.25 %, indicating its adeptness in accurately identifying fertile soil instances. The Recall metric stands at 90.90 %, emphasizing the model's ability to capture true positive cases effectively.

{"title":"Sparse attention regression network-based soil fertility prediction with UMMASO","authors":"RVRaghavendra Rao , U Srinivasulu Reddy","doi":"10.1016/j.chemolab.2024.105289","DOIUrl":"10.1016/j.chemolab.2024.105289","url":null,"abstract":"<div><div>The challenge of imbalanced soil nutrient datasets significantly hampers accurate predictions of soil fertility. To tackle this, a new method is suggested in this research, combining Uniform Manifold Approximation and Projection (UMAP) with Least Absolute Shrinkage and Selection Operator (LASSO). The main aim is to counter the impact of uneven data distribution and improve soil fertility models' predictive precision. The model introduced uses Sparse Attention Regression, effectively incorporating pertinent features from the imbalanced dataset. UMAP is utilised initially to reduce data complexity, unveiling hidden structures and essential patterns. Following this, LASSO is applied to refine features and enhance the model's interpretability. The experimental outcomes highlight the effectiveness of the UMAP and LASSO hybrid approach. The proposed model achieves outstanding performance metrics, reaching a predictive accuracy of 98 %, demonstrating its capability in accurate soil fertility predictions. It also showcases a Precision of 91.25 %, indicating its adeptness in accurately identifying fertile soil instances. The Recall metric stands at 90.90 %, emphasizing the model's ability to capture true positive cases effectively.</div></div>","PeriodicalId":9774,"journal":{"name":"Chemometrics and Intelligent Laboratory Systems","volume":"257 ","pages":"Article 105289"},"PeriodicalIF":3.7,"publicationDate":"2024-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143156199","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multivariate image analysis for assessment of textural attributes in transglutaminase-reconstituted meat 多变量图像分析评价谷氨酰胺转胺酶重组肉的纹理属性

IF 3.7 2区化学 Q2 AUTOMATION & CONTROL SYSTEMS

Chemometrics and Intelligent Laboratory Systems

Pub Date : 2024-11-26 DOI: 10.1016/j.chemolab.2024.105280

Samuel Verdú , Ignacio García , Carlos Roda , José M. Barat , Raúl Grau , Alberto Ferrer , J.M. Prats-Montalbán

The control of sensorial textural attributes has high interest to the meat industry focused on the recovery of the value of meat by-products by developing reconstituted meat pieces with added sensory and nutritional values. Sensorial analysis of foods is still a quite subjective methodology, highly dependent of a well-trained team of inspectors, which is simulated by textural analysis in order to measure objective physical properties. This work presents a non-destructive and contactless experimental methodology to predict the physical properties of a reconstituted meat product, based on integrating multispectral imaging and multivariate image analysis (MIA). The experiment was based on reconstituting grounded meat with different concentrations of transglutaminase (0.1, 1, 3, 6 and 10 %), from which textural properties and multispectral imaging data were measured. Multispectral images (UV, VIS and NIR wavelengths) were processed with chemometric procedures to obtain the distribution maps and score images, from which different blocks of features were extracted to generate feature vectors (basic statistics and co-occurrence matrix) for each image. The obtained regression models built with these features predicted all physical properties of the meat with Q² > 0.90, after feature selection using VIPs. These results evidenced the capacity of multispectral imaging, combined with chemometric procedures, to capture the variability of physical properties induced by transglutaminase in a derivate meat product. It could represent the base of a potential contactless application for a meat industrial inspection, where work environments have strong hygienic requirements.

通过开发具有附加感官和营养价值的重组肉片来回收肉类副产品价值的肉类工业对感官质地属性的控制具有很高的兴趣。食品的感官分析仍然是一种非常主观的方法，高度依赖于训练有素的检查员团队，这是通过质地分析来模拟的，以测量客观的物理特性。本研究提出了一种基于多光谱成像和多变量图像分析（MIA）的非破坏性和非接触式实验方法来预测重构肉制品的物理特性。实验是基于用不同浓度的谷氨酰胺转胺酶（0.1、1、3、6和10%）重构碎肉，并测量其纹理特性和多光谱成像数据。采用化学计量学方法对多光谱图像（UV、VIS和NIR波长）进行处理，得到图像的分布图和评分图，并从中提取不同的特征块，生成每张图像的特征向量（基本统计量和共现矩阵）。利用这些特征建立的回归模型用Q2 >预测了肉的所有物理性质；0.90，使用vip进行特征选择后。这些结果证明了多光谱成像与化学计量程序相结合的能力，可以捕获转谷氨酰胺酶在衍生肉制品中引起的物理特性的可变性。它可能代表了一种潜在的非接触式应用的基础，用于工作环境对卫生有很强要求的肉类工业检查。

{"title":"Multivariate image analysis for assessment of textural attributes in transglutaminase-reconstituted meat","authors":"Samuel Verdú , Ignacio García , Carlos Roda , José M. Barat , Raúl Grau , Alberto Ferrer , J.M. Prats-Montalbán","doi":"10.1016/j.chemolab.2024.105280","DOIUrl":"10.1016/j.chemolab.2024.105280","url":null,"abstract":"<div><div>The control of sensorial textural attributes has high interest to the meat industry focused on the recovery of the value of meat by-products by developing reconstituted meat pieces with added sensory and nutritional values. Sensorial analysis of foods is still a quite subjective methodology, highly dependent of a well-trained team of inspectors, which is simulated by textural analysis in order to measure objective physical properties. This work presents a non-destructive and contactless experimental methodology to predict the physical properties of a reconstituted meat product, based on integrating multispectral imaging and multivariate image analysis (MIA). The experiment was based on reconstituting grounded meat with different concentrations of transglutaminase (0.1, 1, 3, 6 and 10 %), from which textural properties and multispectral imaging data were measured. Multispectral images (UV, VIS and NIR wavelengths) were processed with chemometric procedures to obtain the distribution maps and score images, from which different blocks of features were extracted to generate feature vectors (basic statistics and co-occurrence matrix) for each image. The obtained regression models built with these features predicted all physical properties of the meat with Q<sup>2</sup> > 0.90, after feature selection using VIPs. These results evidenced the capacity of multispectral imaging, combined with chemometric procedures, to capture the variability of physical properties induced by transglutaminase in a derivate meat product. It could represent the base of a potential contactless application for a meat industrial inspection, where work environments have strong hygienic requirements.</div></div>","PeriodicalId":9774,"journal":{"name":"Chemometrics and Intelligent Laboratory Systems","volume":"256 ","pages":"Article 105280"},"PeriodicalIF":3.7,"publicationDate":"2024-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142745558","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Robust adaptive control for nonlinear discrete-time systems based on DE-GMAW 基于 DE-GMAW 的非线性离散时间系统鲁棒自适应控制

IF 3.7 2区化学 Q2 AUTOMATION & CONTROL SYSTEMS

Chemometrics and Intelligent Laboratory Systems

Pub Date : 2024-11-23 DOI: 10.1016/j.chemolab.2024.105274

Jing Wang , Engang Tian , Huaicheng Yan , Fanrong Qu

Gas Metal Arc Welding (GMAW) is a critical process in manufacturing, known for its efficiency and versatility. The double-electrode GMAW (DE-GMAW) technique further enhances these attributes, offering superior welding speed and improved melting effects. However, controlling the DE-GMAW process effectively remains a complex challenge due to the nonlinear and dynamic nature of the system. The process involves intricate interactions between electrical, thermal, and mechanical phenomena, resulting in highly nonlinear behavior. Variations in material properties, environmental conditions, and external disturbances can adversely affect the welding process. Moreover, traditional control methods often fail to account for unmodeled dynamics and modeling errors, leading to performance degradation and potential instability. To address these challenges, this paper introduces a robust adaptive control scheme tailored for DE-GMAW systems, which combines online projection estimation identification and pole placement strategy at the same time to compensate for parameter uncertainties, external disturbances, and unmodeled dynamics. Simulation examples in welding process are carried out to demonstrate the effectiveness of the proposed robust adaptive control scheme.

气体金属弧焊（GMAW）是制造业中的一项重要工艺，以其高效性和多功能性而著称。双电极 GMAW（DE-GMAW）技术进一步增强了这些特性，焊接速度更快，熔化效果更好。然而，由于系统的非线性和动态特性，有效控制 DE-GMAW 过程仍然是一项复杂的挑战。该工艺涉及电、热和机械现象之间错综复杂的相互作用，导致高度非线性行为。材料特性、环境条件和外部干扰的变化会对焊接过程产生不利影响。此外，传统的控制方法往往无法考虑未建模的动态和建模误差，从而导致性能下降和潜在的不稳定性。为应对这些挑战，本文介绍了一种专为 DE-GMAW 系统定制的鲁棒自适应控制方案，该方案同时结合了在线投影估计识别和极点放置策略，以补偿参数不确定性、外部干扰和未建模动态。通过焊接过程中的仿真实例，证明了所提出的鲁棒自适应控制方案的有效性。

{"title":"Robust adaptive control for nonlinear discrete-time systems based on DE-GMAW","authors":"Jing Wang , Engang Tian , Huaicheng Yan , Fanrong Qu","doi":"10.1016/j.chemolab.2024.105274","DOIUrl":"10.1016/j.chemolab.2024.105274","url":null,"abstract":"<div><div>Gas Metal Arc Welding (GMAW) is a critical process in manufacturing, known for its efficiency and versatility. The double-electrode GMAW (DE-GMAW) technique further enhances these attributes, offering superior welding speed and improved melting effects. However, controlling the DE-GMAW process effectively remains a complex challenge due to the nonlinear and dynamic nature of the system. The process involves intricate interactions between electrical, thermal, and mechanical phenomena, resulting in highly nonlinear behavior. Variations in material properties, environmental conditions, and external disturbances can adversely affect the welding process. Moreover, traditional control methods often fail to account for unmodeled dynamics and modeling errors, leading to performance degradation and potential instability. To address these challenges, this paper introduces a robust adaptive control scheme tailored for DE-GMAW systems, which combines online projection estimation identification and pole placement strategy at the same time to compensate for parameter uncertainties, external disturbances, and unmodeled dynamics. Simulation examples in welding process are carried out to demonstrate the effectiveness of the proposed robust adaptive control scheme.</div></div>","PeriodicalId":9774,"journal":{"name":"Chemometrics and Intelligent Laboratory Systems","volume":"256 ","pages":"Article 105274"},"PeriodicalIF":3.7,"publicationDate":"2024-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142719741","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Enhanced satellite image resolution with a residual network and correlation filter 利用残差网络和相关滤波器增强卫星图像分辨率

IF 3.7 2区化学 Q2 AUTOMATION & CONTROL SYSTEMS

Chemometrics and Intelligent Laboratory Systems

Pub Date : 2024-11-22 DOI: 10.1016/j.chemolab.2024.105277

Ajay Sharma , Bhavana P. Shrivastava , Praveen Kumar Tyagi , Ebtasam Ahmad Siddiqui , Rahul Prasad , Swati Gautam , Pranshu Pranjal

This study addresses the predominant challenge of very low-resolution satellite images in remote sensing applications, a common issue in satellite image-based surveillance. Existing satellite image recognition algorithms struggle with such low-resolution images, and traditional Super-Resolution (SR) techniques fall short for very low-resolution cases. We propose the Progressive Satellite Image Super-Resolution (PSISR) model to bridge this gap. Unlike current learning-based SR methods, the PSISR model specifically targets very low-resolution satellite images. In satellite image super-resolution, problems with feature fusion that result in image noise, blind spots, poor perceptual quality, and checkboard artifacts are encountered during the reconstruction process. Current models try to improve perceptual quality, but they frequently show challenges in attaining acceptable outcomes because of losses during reconstruction. Using a combined loss function, correlation filters, and a loss-aware upscaling network layer, the PSISR model presents a revolutionary methodology. The model adopts a cascading structure with dense skip connections, sequentially upscaling images by factors of

2 \times

,

4 \times

, and

8 \times

through three modules. To validate the model's superiority, a study is conducted, confirming its effectiveness compared to baseline models and also training the other models using the available dataset to prove the effectiveness of the model. The PSISR model effectively addresses the challenge of extracting more features with minimal losses, resulting in high magnification during reconstruction. Our method outperforms state-of-the-art techniques, including Swin2-MoSE, MambaFormer, SRFBN and RCAN, with a PSNR improvement of up to 0.4 dB and a 0.003 SSIM enhancement across various datasets. This demonstrates the effectiveness of our approach in producing high-quality outputs, achieving a 99.25 % correlation efficiency between the generated and original images.

本研究解决了遥感应用中极低分辨率卫星图像的主要挑战，这是基于卫星图像的监视中的一个常见问题。现有的卫星图像识别算法难以识别这种低分辨率图像，而传统的超分辨率（SR）技术在非常低分辨率的情况下表现不佳。我们提出了渐进式卫星图像超分辨率（PSISR）模型来弥补这一差距。与目前基于学习的SR方法不同，PSISR模型专门针对非常低分辨率的卫星图像。在卫星图像超分辨率重建过程中，会遇到特征融合导致图像噪声、盲点、感知质量差、棋盘伪影等问题。目前的模型试图提高感知质量，但由于重建过程中的损失，它们在获得可接受的结果方面经常表现出挑战。使用组合损失函数，相关滤波器和损失感知的升级网络层，PSISR模型提出了一种革命性的方法。该模型采用密集跳跃连接的级联结构，通过三个模块依次将图像以2倍、4倍、8倍的倍数进行提升。为了验证模型的优越性，我们进行了一项研究，确认了其与基线模型的有效性，并使用可用的数据集训练其他模型来证明模型的有效性。PSISR模型有效地解决了以最小损失提取更多特征的挑战，从而在重建过程中实现了高放大。我们的方法优于最先进的技术，包括Swin2-MoSE， MambaFormer， SRFBN和RCAN，在各种数据集上的PSNR提高了0.4 dB， SSIM提高了0.003。这证明了我们的方法在产生高质量输出方面的有效性，在生成的图像和原始图像之间实现了99.25%的相关效率。

{"title":"Enhanced satellite image resolution with a residual network and correlation filter","authors":"Ajay Sharma , Bhavana P. Shrivastava , Praveen Kumar Tyagi , Ebtasam Ahmad Siddiqui , Rahul Prasad , Swati Gautam , Pranshu Pranjal","doi":"10.1016/j.chemolab.2024.105277","DOIUrl":"10.1016/j.chemolab.2024.105277","url":null,"abstract":"<div><div>This study addresses the predominant challenge of very low-resolution satellite images in remote sensing applications, a common issue in satellite image-based surveillance. Existing satellite image recognition algorithms struggle with such low-resolution images, and traditional Super-Resolution (SR) techniques fall short for very low-resolution cases. We propose the Progressive Satellite Image Super-Resolution (PSISR) model to bridge this gap. Unlike current learning-based SR methods, the PSISR model specifically targets very low-resolution satellite images. In satellite image super-resolution, problems with feature fusion that result in image noise, blind spots, poor perceptual quality, and checkboard artifacts are encountered during the reconstruction process. Current models try to improve perceptual quality, but they frequently show challenges in attaining acceptable outcomes because of losses during reconstruction. Using a combined loss function, correlation filters, and a loss-aware upscaling network layer, the PSISR model presents a revolutionary methodology. The model adopts a cascading structure with dense skip connections, sequentially upscaling images by factors of <span><math><mrow><mn>2</mn><mo>×</mo></mrow></math></span>, <span><math><mrow><mn>4</mn><mo>×</mo></mrow></math></span>, and <span><math><mrow><mn>8</mn><mo>×</mo></mrow></math></span> through three modules. To validate the model's superiority, a study is conducted, confirming its effectiveness compared to baseline models and also training the other models using the available dataset to prove the effectiveness of the model. The PSISR model effectively addresses the challenge of extracting more features with minimal losses, resulting in high magnification during reconstruction. Our method outperforms state-of-the-art techniques, including Swin2-MoSE, MambaFormer, SRFBN and RCAN, with a PSNR improvement of up to 0.4 dB and a 0.003 SSIM enhancement across various datasets. This demonstrates the effectiveness of our approach in producing high-quality outputs, achieving a 99.25 % correlation efficiency between the generated and original images.</div></div>","PeriodicalId":9774,"journal":{"name":"Chemometrics and Intelligent Laboratory Systems","volume":"256 ","pages":"Article 105277"},"PeriodicalIF":3.7,"publicationDate":"2024-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142745557","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A novel soft sensor approach for industrial quality prediction based TCN with spatial and temporal attention

IF 3.7 2区化学 Q2 AUTOMATION & CONTROL SYSTEMS

Chemometrics and Intelligent Laboratory Systems

Pub Date : 2024-11-22 DOI: 10.1016/j.chemolab.2024.105272

Lei Zhang , Guofeng Ren , Shanlian Li , Jinsong Du , Dayong Xu , Yinhua Li

The complex industrial process is often characterized by strong multivariate coupling and nonlinear dynamic changes, which pose great challenges to modeling and prediction. Traditional deep learning methods are difficult to effectively capture spatiotemporal characteristics of industrial processes, resulting in poor prediction accuracy. To tackle this issue, we propose a novel end-to-end method named STA-TCN, which utilizes a temporal convolutional network (TCN) with both spatial and temporal attention mechanisms. The TCN uses causal and dilated convolutions to capture long temporal patterns in time series data. The spatial attention identifies the significance of different features, while the temporal attention focuses on crucial time steps. This design assigns adaptive weights to different features and emphasizes key moments to improve the accuracy of dynamic processes. We conduct experiments on two industrial datasets and show that the proposed STA-TCN method achieves significantly improved predictive performance compared to TCN for quality prediction of industrial processes. The results validate the effectiveness and robustness of the proposed method.

{"title":"A novel soft sensor approach for industrial quality prediction based TCN with spatial and temporal attention","authors":"Lei Zhang , Guofeng Ren , Shanlian Li , Jinsong Du , Dayong Xu , Yinhua Li","doi":"10.1016/j.chemolab.2024.105272","DOIUrl":"10.1016/j.chemolab.2024.105272","url":null,"abstract":"<div><div>The complex industrial process is often characterized by strong multivariate coupling and nonlinear dynamic changes, which pose great challenges to modeling and prediction. Traditional deep learning methods are difficult to effectively capture spatiotemporal characteristics of industrial processes, resulting in poor prediction accuracy. To tackle this issue, we propose a novel end-to-end method named STA-TCN, which utilizes a temporal convolutional network (TCN) with both spatial and temporal attention mechanisms. The TCN uses causal and dilated convolutions to capture long temporal patterns in time series data. The spatial attention identifies the significance of different features, while the temporal attention focuses on crucial time steps. This design assigns adaptive weights to different features and emphasizes key moments to improve the accuracy of dynamic processes. We conduct experiments on two industrial datasets and show that the proposed STA-TCN method achieves significantly improved predictive performance compared to TCN for quality prediction of industrial processes. The results validate the effectiveness and robustness of the proposed method.</div></div>","PeriodicalId":9774,"journal":{"name":"Chemometrics and Intelligent Laboratory Systems","volume":"257 ","pages":"Article 105272"},"PeriodicalIF":3.7,"publicationDate":"2024-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143156194","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

GATNM: Graph with Attention Neural Network Model for Mycobacterial Cell Wall Permeability of Drugs and Drug-like Compounds GATNM：药物和类药物分枝杆菌细胞壁渗透性的注意力图神经网络模型

IF 3.7 2区化学 Q2 AUTOMATION & CONTROL SYSTEMS

Chemometrics and Intelligent Laboratory Systems

Pub Date : 2024-11-21 DOI: 10.1016/j.chemolab.2024.105265

Agung Surya Wibowo , Osphanie Mentari Primadianti , Hilal Tayara , Kil To Chong

Mycobacterium tuberculosis cell wall has complexity and unusual organization. These conditions make the nutrients and antibiotics difficult to penetrate this wall which affects the low activity of several antimycobacterial drugs in mycobacteria cells. Based on this information, the cell wall permeability prediction in some compounds becomes important and would help develop novel antitubercular drugs. Recently, there have been many predictions helped by computational technology using the Simplified Molecular Input Line Entry System (SMILES) input drug compounds. In this study, we applied computational technology to predict the permeability of cell walls to some compounds or drugs. We evaluated several common machine learning models for their ability to predict cell wall permeability. However, none of these models achieved satisfactory performance. We investigated a Graph with Attention Neural Network (GATNN) model to address this challenge. In the case of permeability detection, to the best of our knowledge, the GATNN model is considered a new approach to improve the prediction performance of the penetration ability of some compounds to the cell wall of the mycobacterial. Additionally, we optimized the accuracy value to get the best hyperparameter and the best model by Optuna. After getting the optimal model, by using the benchmark dataset, this model has slightly increased the performance over the previous model in accuracy and specificity to 78.9% and 81.5%. As a complementary, we also provided an ensemble model and generated the interpretability of the model. The code and materials of all experiments in this paper can be accessed freely at this link: https://github.com/asw1982/MTbPrediction.

结核分枝杆菌的细胞壁具有复杂性和不寻常的组织结构。这些条件使得营养物质和抗生素难以渗透细胞壁，从而影响了多种抗分枝杆菌药物在分枝杆菌细胞中的低活性。基于这些信息，对某些化合物的细胞壁渗透性进行预测就变得非常重要，这将有助于开发新型抗结核药物。最近，利用简化分子输入行输入系统（SMILES）输入药物化合物的计算技术帮助进行了许多预测。在本研究中，我们应用计算技术来预测细胞壁对某些化合物或药物的渗透性。我们评估了几种常见的机器学习模型预测细胞壁渗透性的能力。然而，这些模型都没有达到令人满意的性能。我们研究了一种注意力图神经网络（GATNN）模型来应对这一挑战。就渗透性检测而言，据我们所知，GATNN 模型被认为是提高某些化合物对分枝杆菌细胞壁渗透能力预测性能的一种新方法。此外，我们还通过 Optuna 优化了准确度值，以获得最佳超参数和最佳模型。获得最佳模型后，通过使用基准数据集，该模型的准确率和特异性比之前的模型略有提高，分别达到 78.9% 和 81.5%。作为补充，我们还提供了一个集合模型，并生成了模型的可解释性。本文中所有实验的代码和材料均可从以下链接免费获取：https://github.com/asw1982/MTbPrediction。

{"title":"GATNM: Graph with Attention Neural Network Model for Mycobacterial Cell Wall Permeability of Drugs and Drug-like Compounds","authors":"Agung Surya Wibowo , Osphanie Mentari Primadianti , Hilal Tayara , Kil To Chong","doi":"10.1016/j.chemolab.2024.105265","DOIUrl":"10.1016/j.chemolab.2024.105265","url":null,"abstract":"<div><div><em>Mycobacterium tuberculosis</em> cell wall has complexity and unusual organization. These conditions make the nutrients and antibiotics difficult to penetrate this wall which affects the low activity of several antimycobacterial drugs in mycobacteria cells. Based on this information, the cell wall permeability prediction in some compounds becomes important and would help develop novel antitubercular drugs. Recently, there have been many predictions helped by computational technology using the Simplified Molecular Input Line Entry System (SMILES) input drug compounds. In this study, we applied computational technology to predict the permeability of cell walls to some compounds or drugs. We evaluated several common machine learning models for their ability to predict cell wall permeability. However, none of these models achieved satisfactory performance. We investigated a Graph with Attention Neural Network (GATNN) model to address this challenge. In the case of permeability detection, to the best of our knowledge, the GATNN model is considered a new approach to improve the prediction performance of the penetration ability of some compounds to the cell wall of the mycobacterial. Additionally, we optimized the accuracy value to get the best hyperparameter and the best model by Optuna. After getting the optimal model, by using the benchmark dataset, this model has slightly increased the performance over the previous model in accuracy and specificity to 78.9% and 81.5%. As a complementary, we also provided an ensemble model and generated the interpretability of the model. The code and materials of all experiments in this paper can be accessed freely at this link: <span><span>https://github.com/asw1982/MTbPrediction</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":9774,"journal":{"name":"Chemometrics and Intelligent Laboratory Systems","volume":"256 ","pages":"Article 105265"},"PeriodicalIF":3.7,"publicationDate":"2024-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142719739","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A review of quantitative structure-activity relationship: The development and current status of data sets, molecular descriptors and mathematical models 定量结构-活性关系综述：数据集、分子描述符和数学模型的发展与现状

IF 3.7 2区化学 Q2 AUTOMATION & CONTROL SYSTEMS

Chemometrics and Intelligent Laboratory Systems

Pub Date : 2024-11-21 DOI: 10.1016/j.chemolab.2024.105278

Jianmin Li , Tian Zhao , Qin Yang , Shijie Du , Lu Xu

Developing Quantitative Structure-Activity Relationship (QSAR) models applicable to general molecules is of great significance for molecular design in many disciplines. This paper reviews the development and current status of molecular QSAR research, including datasets, molecular descriptors, and mathematical models. A representative bibliometric analysis reveals the evolutionary trends in this field in the past decade. Based on the discussion of the advantages and shortcomings of existing methods, the requirements and possible approaches for developing a widely applicable QSAR model were put forward. This goal poses a series of challenges to QSAR, including: (1) Having a sufficient number of structure-activity relationship instances as training data to cope with the complexity and diversity of molecular structures and action mechanisms; (2) Developing and using precise molecular descriptors to avoid the situation of ‘garbage in, garbage out’, while balancing descriptor dimensions and computational costs; and (3) Using powerful and flexible mathematical models, such as deep learning models, to learn complex functional relationships between descriptors and activity. With the emergence of larger and higher-quality data sets, more accurate molecular descriptors and deep learning methods, predictive ability, interpretability and application domain of QSAR models will continue to improve, and it will play a more important role in various fields of molecular design.

开发适用于一般分子的定量结构-活性关系（QSAR）模型对许多学科的分子设计具有重要意义。本文回顾了分子 QSAR 研究的发展和现状，包括数据集、分子描述符和数学模型。一项具有代表性的文献计量分析揭示了过去十年该领域的演变趋势。在讨论现有方法的优势和不足的基础上，提出了开发广泛应用的 QSAR 模型的要求和可能的方法。这一目标对 QSAR 提出了一系列挑战，包括：（1）拥有足够数量的结构-活性关系实例作为训练数据，以应对分子结构和作用机制的复杂性和多样性；（2）开发和使用精确的分子描述符，以避免 "垃圾进，垃圾出 "的情况，同时平衡描述符维度和计算成本；以及（3）使用强大而灵活的数学模型，如深度学习模型，来学习描述符和活性之间复杂的功能关系。随着更大、更高质量的数据集、更精确的分子描述符和深度学习方法的出现，QSAR 模型的预测能力、可解释性和应用领域将不断提高，并将在分子设计的各个领域发挥更重要的作用。

{"title":"A review of quantitative structure-activity relationship: The development and current status of data sets, molecular descriptors and mathematical models","authors":"Jianmin Li , Tian Zhao , Qin Yang , Shijie Du , Lu Xu","doi":"10.1016/j.chemolab.2024.105278","DOIUrl":"10.1016/j.chemolab.2024.105278","url":null,"abstract":"<div><div>Developing Quantitative Structure-Activity Relationship (QSAR) models applicable to general molecules is of great significance for molecular design in many disciplines. This paper reviews the development and current status of molecular QSAR research, including datasets, molecular descriptors, and mathematical models. A representative bibliometric analysis reveals the evolutionary trends in this field in the past decade. Based on the discussion of the advantages and shortcomings of existing methods, the requirements and possible approaches for developing a widely applicable QSAR model were put forward. This goal poses a series of challenges to QSAR, including: (1) Having a sufficient number of structure-activity relationship instances as training data to cope with the complexity and diversity of molecular structures and action mechanisms; (2) Developing and using precise molecular descriptors to avoid the situation of ‘garbage in, garbage out’, while balancing descriptor dimensions and computational costs; and (3) Using powerful and flexible mathematical models, such as deep learning models, to learn complex functional relationships between descriptors and activity. With the emergence of larger and higher-quality data sets, more accurate molecular descriptors and deep learning methods, predictive ability, interpretability and application domain of QSAR models will continue to improve, and it will play a more important role in various fields of molecular design.</div></div>","PeriodicalId":9774,"journal":{"name":"Chemometrics and Intelligent Laboratory Systems","volume":"256 ","pages":"Article 105278"},"PeriodicalIF":3.7,"publicationDate":"2024-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142719740","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

VAE-SIMCA — Data-driven method for building one class classifiers with variational autoencoders VAE-SIMCA - 利用变异自动编码器构建一类分类器的数据驱动方法

IF 3.7 2区化学 Q2 AUTOMATION & CONTROL SYSTEMS

Chemometrics and Intelligent Laboratory Systems

Pub Date : 2024-11-19 DOI: 10.1016/j.chemolab.2024.105276

Akam Petersen, Sergey Kucheryavskiy

The paper proposes a new method for building one class classifiers based on variational autoencoders (VAE). The classification decision is built on a linear combination of two squared distances: computed for the original and the reconstructed image as well as for the representation of the original image inside the latent space formed by VAE. Because both distances are well approximated by scaled chi-square distribution, the decision boundary is computed using the theoretical quantile function for this distribution and the predefined probability for Type I error, ⍺. Thereby the boundary does not require any specific optimization and is solely based on the model outcomes computed for the training set.

The original idea of the proposed method is inherited from another OCC approach, Data Driven Soft Independent Method for Class Analogies, where singular value decomposition is employed for building the latent space. In this paper we show how this idea can be adopted to be used with VAE for detection of anomalies on images. The paper describes the theoretical background, introduces the main outcomes as well as tools for visual exploration of the classification results, and shows how the method works on several simulated and real datasets.

本文提出了一种基于变异自动编码器（VAE）建立一类分类器的新方法。分类决策建立在两个平方距离的线性组合上：计算原始图像和重建图像的平方距离，以及原始图像在 VAE 形成的潜空间内的表示平方距离。由于这两个距离都能很好地近似于按比例的奇平方分布，因此决策边界是使用该分布的理论量子函数和预定义的 I 类错误概率⍺来计算的。因此，边界不需要任何特定的优化，只需根据训练集计算出的模型结果来确定。本文提出的方法的原始思想继承自另一种 OCC 方法，即类类比的数据驱动软独立方法（Data Driven Soft Independent Method for Class Analogies），该方法采用奇异值分解来构建潜在空间。在本文中，我们展示了如何将这一想法与 VAE 一起用于图像异常检测。本文描述了理论背景，介绍了主要成果以及可视化探索分类结果的工具，并展示了该方法如何在多个模拟和真实数据集上运行。

{"title":"VAE-SIMCA — Data-driven method for building one class classifiers with variational autoencoders","authors":"Akam Petersen, Sergey Kucheryavskiy","doi":"10.1016/j.chemolab.2024.105276","DOIUrl":"10.1016/j.chemolab.2024.105276","url":null,"abstract":"<div><div>The paper proposes a new method for building one class classifiers based on variational autoencoders (VAE). The classification decision is built on a linear combination of two squared distances: computed for the original and the reconstructed image as well as for the representation of the original image inside the latent space formed by VAE. Because both distances are well approximated by scaled chi-square distribution, the decision boundary is computed using the theoretical quantile function for this distribution and the predefined probability for Type I error, ⍺. Thereby the boundary does not require any specific optimization and is solely based on the model outcomes computed for the training set.</div><div>The original idea of the proposed method is inherited from another OCC approach, Data Driven Soft Independent Method for Class Analogies, where singular value decomposition is employed for building the latent space. In this paper we show how this idea can be adopted to be used with VAE for detection of anomalies on images. The paper describes the theoretical background, introduces the main outcomes as well as tools for visual exploration of the classification results, and shows how the method works on several simulated and real datasets.</div></div>","PeriodicalId":9774,"journal":{"name":"Chemometrics and Intelligent Laboratory Systems","volume":"256 ","pages":"Article 105276"},"PeriodicalIF":3.7,"publicationDate":"2024-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142719850","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0